Attention. A pre-trained model is downloaded from my cloud (which has its limits). Due to the large number of users, the necessary files are temporarily frozen. Therefore, the algorithm may throw an error.
Check how it works on Google Colab:
- Russian Language
- Bad English Translation
If there are errors, you can find a solution HERE
Based on: first-order-model
The videos on the left show the driving videos. The first row on the right for each dataset shows the source videos. The bottom row contains the animated sequences with motion transferred from the driving video and object taken from the source image.
In addition, there are:
Result Example:
